Instructions to use LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData")
model = AutoModelForCausalLM.from_pretrained("LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData

SGLang

How to use LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData with Docker Model Runner:
```
docker model run hf.co/LLM-OS-Models/LFM2-24B-A2B-Terminal-SFT-2Epoch-HF-FSDP-2BData
```

gyung commited on 22 days ago

Commit

2bacfa2

verified ·

1 Parent(s): b3c7de7

Add epoch 2 (final) checkpoint

Browse files

Files changed (6) hide show

README.md +2 -2
checkpoint-1468/config.json +77 -0
checkpoint-1468/generation_config.json +7 -0
checkpoint-1468/model-00001-of-00002.safetensors +3 -0
checkpoint-1468/model-00002-of-00002.safetensors +3 -0
model-00001-of-00002.safetensors +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ tags:
 - Base model: `LiquidAI/LFM2-24B-A2B`
 - Source output root: `/home/work/.data/qwen_sft/models/LiquidAI__LFM2-24B-A2B__terminal_sft_2epoch_hf_fsdp`
 - Root export copied from: `final`
-- Included checkpoints: `checkpoint-734`
 ## Layout
@@ -26,7 +26,7 @@ tags:
 ## Notes
-Epoch 1 checkpoint
 ## Loading

 - Base model: `LiquidAI/LFM2-24B-A2B`
 - Source output root: `/home/work/.data/qwen_sft/models/LiquidAI__LFM2-24B-A2B__terminal_sft_2epoch_hf_fsdp`
 - Root export copied from: `final`
+- Included checkpoints: `checkpoint-1468`
 ## Layout
 ## Notes
+Epoch 2 (final) checkpoint
 ## Loading

checkpoint-1468/config.json ADDED Viewed

	@@ -0,0 +1,77 @@

+{
+  "architectures": [
+    "Lfm2MoeForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "dtype": "float32",
+  "eos_token_id": 7,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11776,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2_moe",
+  "moe_intermediate_size": 1536,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_dense_layers": 2,
+  "num_experts": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "use_expert_bias": true,
+  "vocab_size": 65536
+}

checkpoint-1468/generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "5.5.0"
+}

checkpoint-1468/model-00001-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b93f9bf0f1264032377c22c878f9690d754aadb1c35d467d1a429c94de3731b
+size 49722124976

checkpoint-1468/model-00002-of-00002.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:57f18e6cb0f69fc085e2e15e9dc456d3c4771d37e1ae236767872fe0f80891e0
+size 46190362888

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8f1e2f73a1f60c433caadbe182d5e68c5db71b3c1dabbccc298ac4e443369f
 size 49722124976

 version https://git-lfs.github.com/spec/v1
+oid sha256:7b93f9bf0f1264032377c22c878f9690d754aadb1c35d467d1a429c94de3731b
 size 49722124976